diff --git a/README.md b/README.md index d9de38d..7d98f84 100644 --- a/README.md +++ b/README.md @@ -36,10 +36,15 @@ python fccs_scan.py Reads the restored FCCS backup directory and writes all drawer IDs (subfolder names) to `drawer_ids.txt`. It also: -- **Flags prefix clashes** — if one drawer ID is a prefix of another (e.g. `02218` and `02218A`), searching the shorter ID in FCCS pops up a selection box that breaks automated navigation. These are reported so you can export them manually or ignore the shorter ID. +- **Flags prefix clashes** — if one drawer ID is a prefix of another (e.g. `02218` and `02218A`), searching the shorter ID in FCCS pops up a selection box that breaks automated navigation. These clashes are reported, and the shorter (prefix) IDs are auto-seeded into `ignore.txt` for review. - **Reports ignored drawers** — any IDs listed in `ignore.txt` that exist in this backup are shown as ones the export will skip. -**Ignoring drawers:** To exclude specific drawers from export (e.g. password-protected folders that would stall the automation), add their IDs to the file at `ignore_file` (default `C:\Migration\ignore.txt`), one per line. `drawer_ids.txt` stays a full inventory; the export skips anything in the ignore list. Lines starting with `#` are treated as comments. +**Ignoring drawers:** The scan creates `ignore.txt` (at `ignore_file`, default `C:\Migration\ignore.txt`) if it doesn't exist and pre-fills it with the clash prefixes — searching those in FCCS shows a selection box that stalls the automation, so they're skipped by default. Open the file and: + +- **Delete or comment out** any clash prefix you actually want exported (then handle it manually in FCCS). +- **Add** any other drawers to skip (e.g. password-protected folders), one ID per line. + +Re-running the scan never overwrites your edits — it only appends newly-discovered clashes. `drawer_ids.txt` stays a full inventory; the export skips anything active in the ignore list. Lines starting with `#` are comments. ### Step 2: Export Documents diff --git a/__pycache__/fccs_scan.cpython-313.pyc b/__pycache__/fccs_scan.cpython-313.pyc new file mode 100644 index 0000000..b210fde Binary files /dev/null and b/__pycache__/fccs_scan.cpython-313.pyc differ diff --git a/fccs_scan.py b/fccs_scan.py index 666cc6d..597e548 100644 --- a/fccs_scan.py +++ b/fccs_scan.py @@ -13,6 +13,61 @@ from fccs_config import ( ) +_IGNORE_HEADER = [ + "# Drawer IDs to SKIP during export (one ID per line).", + "# Lines starting with # are comments and are ignored.", + "#", + "# Add password-protected or otherwise-excluded drawers here.", + "#", + "# The IDs auto-added below are prefix clashes: searching them in FCCS", + "# pops a selection box that breaks the automation, so they're skipped by", + "# default. DELETE or comment out any you actually DO want exported (then", + "# handle them manually), and keep the rest.", + "", +] + + +def update_ignore_file(ignore_file, clashes, log): + """Create ignore.txt if missing and seed it with clash prefix IDs. + + Never overwrites existing entries — only appends clash prefixes that + aren't already present. The shorter (prefix) ID of each clash is the one + that triggers the FCCS selection box, so it's the candidate to skip. + Returns the list of IDs that were added. + """ + existing = set(load_lines(ignore_file)) + file_exists = os.path.exists(ignore_file) + + to_add = [(short, matches) for short, matches in clashes + if short not in existing] + + # Existing file already covers every clash — leave it untouched. + if file_exists and not to_add: + return [] + + lines = [] + if not file_exists: + lines.extend(_IGNORE_HEADER) + + for short, matches in to_add: + lines.append(f"# clashes with: {', '.join(matches)}") + lines.append(short) + + mode = "a" if file_exists else "w" + with open(ignore_file, mode, encoding="utf-8") as f: + if file_exists: + f.write("\n") # separate the new block from prior content + f.write("\n".join(lines) + "\n") + + added = [short for short, _ in to_add] + if not file_exists: + log(f"Created ignore file: {ignore_file}") + if added: + log(f"Added {len(added)} clash prefix ID(s) to ignore list: " + f"{', '.join(added)}") + return added + + def main(): args = parse_args() cfg = load_config(args.config) @@ -37,14 +92,6 @@ def main(): log(f"Found {len(drawer_ids)} drawers, written to {output_file}") - # Report which drawers are set to be ignored (skipped by the export). - ignored = set(load_lines(ignore_file)) - if ignored: - present = sorted(ignored & set(drawer_ids)) - log(f"Ignore list ({ignore_file}): {len(ignored)} IDs, " - f"{len(present)} present in this backup — these will be SKIPPED " - f"by fccs_export.py: {', '.join(present) if present else '(none present)'}") - # Flag prefix clashes: FCCS search on the shorter ID pops a selection box. clashes = check_for_clashes(drawer_ids) if clashes: @@ -52,15 +99,23 @@ def main(): log(f"WARNING: {len(clashes)} potential drawer ID clash(es) found.") log("Searching the shorter ID in FCCS may show a selection box " "instead of navigating directly, which breaks the export.") - log("Consider exporting these manually, or add the shorter ID to " - f"the ignore list ({ignore_file}).") for short, matches in clashes: - flag = " [ignored]" if short in ignored else "" - log(f" {short}{flag} -> also matches: {', '.join(matches)}") + log(f" {short} -> also matches: {', '.join(matches)}") + # Seed ignore.txt with the clash prefixes for review (never overwrites). + update_ignore_file(ignore_file, clashes, log) + log(f"Review the ignore list: {ignore_file}") log("-" * 60) else: log("No drawer ID prefix clashes found.") + # Report which drawers will be skipped by the export. + ignored = set(load_lines(ignore_file)) + if ignored: + present = sorted(ignored & set(drawer_ids)) + log(f"Ignore list ({ignore_file}): {len(ignored)} IDs listed, " + f"{len(present)} present in this backup — these will be SKIPPED " + f"by fccs_export.py: {', '.join(present) if present else '(none present)'}") + if __name__ == "__main__": main()